SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

TL;DR

SelfOcc introduces a self-supervised approach for 3D occupancy prediction in autonomous driving, leveraging video sequences and 3D representations without requiring laborious voxel annotations, achieving state-of-the-art results.

Contribution

It is the first self-supervised method for 3D occupancy prediction from surround cameras, using signed distance fields and multi-view rendering for training.

Findings

Outperforms previous methods by 58.7% on SemanticKITTI

First to produce reasonable 3D occupancy for surround cameras on nuScenes

Achieves state-of-the-art results in depth estimation tasks

Abstract

3D occupancy prediction is an important task for the robustness of vision-centric autonomous driving, which aims to predict whether each point is occupied in the surrounding 3D space. Existing methods usually require 3D occupancy labels to produce meaningful results. However, it is very laborious to annotate the occupancy status of each voxel. In this paper, we propose SelfOcc to explore a self-supervised way to learn 3D occupancy using only video sequences. We first transform the images into the 3D space (e.g., bird's eye view) to obtain 3D representation of the scene. We directly impose constraints on the 3D representations by treating them as signed distance fields. We can then render 2D images of previous and future frames as self-supervision signals to learn the 3D representations. We propose an MVS-embedded strategy to directly optimize the SDF-induced weights with multiple depth proposals. Our SelfOcc outperforms the previous best method SceneRF by 58.7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes. SelfOcc produces high-quality depth and achieves state-of-the-art results on novel depth synthesis, monocular depth estimation, and surround-view depth estimation on the SemanticKITTI, KITTI-2015, and nuScenes, respectively. Code: https://github.com/huang-yh/SelfOcc.